INDEX

Explanations

terms associated with experimental research and findings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸£à¸ģ

-0.17

strcasecmp

-0.16

ni

-0.15

 Watts

-0.15

Ð°Ð½ÑĮ

-0.15

bling

-0.15

.rmi

-0.14

éĳ

-0.14

 Samar

-0.14

Translations

-0.14

POSITIVE LOGITS

yers

0.17

inct

0.15

ERCHANT

0.14

 ober

0.14

abant

0.14

:CGRect

0.14

 tang

0.14

 inout

0.13

\API

0.13

Ð½Ð°ÑĢÐ¾Ð´

0.13

Activations Density 0.031%

terms associated with experimental research and findings

No Comments

No Known Activations